Issue link: https://iconnect007.uberflip.com/i/1530269
DECEMBER 2024 I DESIGN007 MAGAZINE 23 lations and selects the final solution based on the objective function. If specified by the user, ISOP can generate multiple design candidates ranked by FoM in the roll-out stage. A separate surrogate model, functioning as an "evaluator" assesses the reduced candidate space generated in the first stage. is evaluation process elimi- nates inaccurate and uncertain solutions guided by a user-defined coverage level. e key innovation of this process lies in the successful integration of conformal infer- ence (predictions), enabling seamless inter- actions between two machine-learning surro- gates. One surrogate acts as a forward problem proxy, identifying promising solutions, while the other plays an advisory role, effectively eliminating inaccurate or uncertain outcomes. e advantages of this framework over tra- ditional single-stage inverse problems are two- fold. First, it circumvents the need for intensive hyper-parameter optimization, as the evalua- tor model filters out undesired solutions in the second stage. Second, the framework exhibits remarkable applicability across a wide range of problems, owing to conformal inference's min- imal distributional and model assumptions. By integrating conformal inference with any stan- dard regression model, the framework readily provides prediction intervals, making it versa- tile and readily adaptable. Another promising research focus involves designing advanced protocols that enable more than two machine learning surrogates to " e inverse stackup design optimization aims to find the optimal set of design parameters for each signal layer of a PCB stackup simultaneously. " trace width, clearance, and dielectric properties in inverse optimization. e inverse stackup design optimization aims to find the optimal set of design parameters for each signal layer of a PCB stackup simultane- ously. e final stackup design must meet per- formance specifications and optimize a speci- fied performance FoM objective function. Both the constraints and FoM are from performance metrics and are non-trivial to evaluate. e tra- ditional manual design flow relies on a design- er's experience and a trial-and-error approach using multiple simulations. However, ISOP offers a more efficient and automated alterna- tive. e ISOP framework solves the inverse PCB stackup optimization by incorporating a discrete domain HPO. Figure 2 shows an illus- tration of the overall process flow. e HPO process begins with a user-defined function, a set of performance constraints, and parameter search spaces as inputs, then gener- ates the stackup design parameters. It consists of two stages: Early search exploration Globally, sampling parameters in the first stage allow for the exploration of the search space. Instead of relying on time-consuming EM simulations, it uses performance met- rics from a machine learning (ML) surrogate model (approximation model). is approach allows for more samples to be evaluated and a rapid reduction of the search space, albeit with some accuracy trade-offs. is method is akin to reducing the simulation time of a 2D BEM field solver by narrowing the solution space to expedite impedance calculations. A machine learning model termed the "learner" then identifies a limited set of candidates within the input design space whose predicted outputs closely align with desired outcomes. Candidate roll-out e second stage selects the final stackup design based on the initial results. e HPO then evaluates the designs with accurate EM simu-